Comments (6)
你好,
- 这里的描述是勘误, 确实使用的是channel-wise的高斯分布, 感谢指出, 后续会修正. 高斯分布会比较贴切数据的原始分布, 在效果上应该会比fully factorized density model更好 (经验性的), 但对整体模型的性能影响不大.
- 假设训练策略和其他的结构都没问题的话, 我能想到的可能的原因有两点: 1). 加载我的预训练模型之后, fully factorized density model是重新初始化的, 可能在训练初始的时候会使得context model和hyperprior model失衡, 这里你可以check一下bpp_z是否正常. 2). 图片输入的范围 [-1,1] -> [0,1], 这一块可能会影响到Transformer结构的优化.
from entroformer.
from entroformer.
你好!感谢您的回复!
确实有可能是加载预训练权重的问题,我也正在尝试从头开始训练,看看是否会有提升。
非常感谢您的工作!祝好!
from entroformer.
@mx54039q
你好!阅读代码时发现该处self.dim是不是应该改成self.key_value_proj_dim,即多头注意力的dk取64而非384
entroformer/module/entroformer_helper.py
Line 115 in 1c359bf
from entroformer.
你说的没错, 这一块看来是我的实现错误, 不过训练影响不大. 你可以修改一下, 如果有正向提升的话麻烦告知我一下, 谢谢. :)
from entroformer.
@mx54039q
我已经找到了之前训练效果不佳的原因,之前训练时我对于y只用了add noise的操作,没有用ste。 由于我只用bidirectional,于是我把forward过程做到和compress,decompress一致,无需add noise操作。 在compressai的编码方案中,我使用了quantize_ste(y - means_hat) + means_hat
。
我将图像输入域改为了[-1,1],筛选了1.5W张图片作为数据集,加载了您的权重,目前训练了两个模型,效果还不错。在Kodak上compress/decompress的结果如下:
λ=0.02 bpp:0.607 PSNR:35.275
λ=0.18 bpp:1.623 PSNR: 41.401
应该与您paper的结果很相近了。
我现在正在尝试您的random mask的pretrain方案。我修改了dk进行pretrain,然后看看finetune的效果如何,再与您交流^-^
from entroformer.
Related Issues (18)
- When will the code be revealed? HOT 2
- Decompressed HOT 4
- 为什么用不同的预训练模型,得到的二进制文件的大小都是一样的 HOT 3
- torchac 中的BitInputStream类 HOT 3
- 关于parallel模型的RD数据 HOT 1
- 关于bpp的计算
- 关于bpp的计算 HOT 2
- 请问您在编码部分,为什么要将图像乘2再减1呢 HOT 4
- Inquiry: Extending Model Capability for High Resolution Image Compression HOT 2
- 运行demo时出现valueerror
- I can't wait to see the code!friends, hurry up! HOT 1
- About pretrain and finetune HOT 5
- The RD points on Kodak HOT 4
- Compressed binary file size HOT 7
- Kodak dataset 在低码率上就达到很高的psnr HOT 4
- Checkpoint for psnr = 37.72 HOT 3
- 训练集的获取与图片选择 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from entroformer.